2022-10-12
While new car models come out and discontinued each year, some model remains to be long time seller. For this project, I will dive into identify what characteristic does the top sold car have/what do consumers look for when buying a car.
More information can be found here below. https://www.kaggle.com/datasets/gagandeep16/car-sales
library(plotly)
library(dplyr)
df<- read.csv("Car_sales.csv")
df <- subset(df,select =-Vehicle_type)
Every plot was generated using plotly
glimpse(df)
## Rows: 157 ## Columns: 15 ## $ Manufacturer <chr> "Acura", "Acura", "Acura", "Acura", "Audi", "Audi… ## $ Model <chr> "Integra", "TL", "CL", "RL", "A4", "A6", "A8", "3… ## $ Sales_in_thousands <dbl> 16.919, 39.384, 14.114, 8.588, 20.397, 18.780, 1.… ## $ X__year_resale_value <dbl> 16.360, 19.875, 18.225, 29.725, 22.255, 23.555, 3… ## $ Price_in_thousands <dbl> 21.500, 28.400, NA, 42.000, 23.990, 33.950, 62.00… ## $ Engine_size <dbl> 1.8, 3.2, 3.2, 3.5, 1.8, 2.8, 4.2, 2.5, 2.8, 2.8,… ## $ Horsepower <int> 140, 225, 225, 210, 150, 200, 310, 170, 193, 193,… ## $ Wheelbase <dbl> 101.2, 108.1, 106.9, 114.6, 102.6, 108.7, 113.0, … ## $ Width <dbl> 67.3, 70.3, 70.6, 71.4, 68.2, 76.1, 74.0, 68.4, 6… ## $ Length <dbl> 172.4, 192.9, 192.0, 196.6, 178.0, 192.0, 198.2, … ## $ Curb_weight <dbl> 2.639, 3.517, 3.470, 3.850, 2.998, 3.561, 3.902, … ## $ Fuel_capacity <dbl> 13.2, 17.2, 17.2, 18.0, 16.4, 18.5, 23.7, 16.6, 1… ## $ Fuel_efficiency <int> 28, 25, 26, 22, 27, 22, 21, 26, 24, 25, 25, 23, 2… ## $ Latest_Launch <chr> "2/2/2012", "6/3/2011", "1/4/2012", "3/10/2011", … ## $ Power_perf_factor <dbl> 58.28015, 91.37078, NA, 91.38978, 62.77764, 84.56…
Ford F-seiries seems to be the favorite by far.(possibly counting every F-series line up )
select(df, Manufacturer, Model, Sales_in_thousands) %>% arrange(desc(Sales_in_thousands))
## Manufacturer Model Sales_in_thousands ## 1 Ford F-Series 540.561 ## 2 Ford Explorer 276.747 ## 3 Toyota Camry 247.994 ## 4 Ford Taurus 245.815 ## 5 Honda Accord 230.902 ## 6 Dodge Ram Pickup 227.061 ## 7 Ford Ranger 220.650 ## 8 Honda Civic 199.685 ## 9 Dodge Caravan 181.749 ## 10 Ford Focus 175.670 ## 11 Jeep Grand Cherokee 157.040 ## 12 Ford Windstar 155.787 ## 13 Chevrolet Cavalier 145.519 ## 14 Toyota Corolla 142.535 ## 15 Chevrolet Malibu 135.126 ## 16 Pontiac Grand Am 131.097 ## 17 Ford Expedition 125.338 ## 18 Ford Mustang 113.369 ## 19 Dodge Dakota 111.313 ## 20 Chevrolet Impala 107.995 ## 21 Dodge Durango 101.323 ## 22 Pontiac Grand Prix 92.364 ## 23 Buick Century 91.561 ## 24 Nissan Altima 88.094 ## 25 Dodge Intrepid 88.028 ## 26 Toyota Tacoma 84.087 ## 27 Volkswagen Jetta 83.721 ## 28 Buick LeSabre 83.257 ## 29 Mercury Grand Marquis 81.174 ## 30 Saturn SL 80.620 ## 31 Jeep Cherokee 80.556 ## 32 Oldsmobile Alero 80.255 ## 33 Nissan Maxima 79.853 ## 34 Dodge Neon 76.034 ## 35 Honda Odyssey 76.029 ## 36 Honda CR-V 73.203 ## 37 Dodge Stratus 71.186 ## 38 Ford Escort 70.227 ## 39 Toyota 4Runner 68.411 ## 40 Mercury Sable 67.956 ## 41 Hyundai Elantra 66.692 ## 42 Toyota Sienna 65.119 ## 43 Nissan Frontier 65.005 ## 44 Toyota Avalon 63.849 ## 45 Cadillac DeVille 63.729 ## 46 Ford Crown Victoria 63.403 ## 47 Mitsubishi Galant 55.616 ## 48 Jeep Wrangler 55.557 ## 49 Nissan Xterra 54.158 ## 50 Chrysler Town & Country 53.480 ## 51 Pontiac Sunfire 51.645 ## 52 Lexus RX300 51.238 ## 53 Volkswagen Passat 51.102 ## 54 Saturn LS 49.989 ## 55 Volkswagen Beetle 49.463 ## 56 Lincoln Town car 48.911 ## 57 Subaru Outback 47.107 ## 58 Nissan Sentra 42.643 ## 59 Chevrolet Monte Carlo 42.593 ## 60 Nissan Pathfinder 42.574 ## 61 Mitsubishi Eclipse 42.541 ## 62 Hyundai Accent 41.184 ## 63 Pontiac Montana 39.572 ## 64 Acura TL 39.384 ## 65 Buick Regal 39.350 ## 66 Mitsubishi Montero Sport 39.348 ## 67 Oldsmobile Intrigue 38.554 ## 68 Pontiac Bonneville 35.945 ## 69 Ford Contour 35.068 ## 70 Toyota Celica 33.269 ## 71 Subaru Forester 33.028 ## 72 Chrysler Sebring Conv. 32.775 ## 73 Plymouth Neon 32.734 ## 74 Chrysler Cirrus 32.306 ## 75 Chevrolet Prizm 32.299 ## 76 Chrysler Concorde 31.148 ## 77 Dodge Ram Van 31.038 ## 78 Chrysler 300M 30.696 ## 79 Hyundai Sonata 29.450 ## 80 Mercedes-B M-Class 28.976 ## 81 Buick Park Avenue 27.851 ## 82 Mercury Mountaineer 27.609 ## 83 Mercedes-B E-Class 27.602 ## 84 Nissan Quest 27.308 ## 85 Mercury Cougar 26.529 ## 86 Chevrolet Camaro 26.402 ## 87 Mitsubishi Mirage 26.232 ## 88 Toyota RAV4 25.106 ## 89 Chevrolet Lumina 24.629 ## 90 Saturn SC 24.546 ## 91 Oldsmobile Silhouette 24.361 ## 92 Plymouth Voyager 24.155 ## 93 Lexus ES300 24.072 ## 94 Infiniti I30 23.713 ## 95 Lincoln Navigator 22.925 ## 96 Chevrolet Metro 21.855 ## 97 Audi A4 20.397 ## 98 Mercury Villager 20.380 ## 99 Oldsmobile Bravada 20.017 ## 100 Pontiac Firebird 19.911 ## 101 BMW 323i 19.747 ## 102 Volvo S80 18.969 ## 103 Audi A6 18.780 ## 104 Mercedes-B C-Class 18.392 ## 105 Chevrolet Corvette 17.947 ## 106 Volvo V70 17.531 ## 107 BMW 528i 17.527 ## 108 Volvo S40 16.957 ## 109 Acura Integra 16.919 ## 110 Mercedes-B S-Class 16.774 ## 111 Dodge Ram Wagon 16.767 ## 112 Cadillac Seville 15.943 ## 113 Jaguar S-Type 15.467 ## 114 Volvo S70 15.245 ## 115 Cadillac Escalade 14.785 ## 116 Oldsmobile Aurora 14.690 ## 117 Mercury Mystique 14.351 ## 118 Acura CL 14.114 ## 119 Lincoln Continental 13.798 ## 120 Chrysler LHS 13.462 ## 121 Honda Passport 12.855 ## 122 Lexus GS300 12.698 ## 123 Saab 3-Sep 12.115 ## 124 Mercedes-B CLK Coupe 11.592 ## 125 Mitsubishi Montero 11.337 ## 126 Cadillac Catera 11.185 ## 127 Toyota Land Cruiser 9.835 ## 128 Volkswagen Golf 9.761 ## 129 Volkswagen Cabrio 9.569 ## 130 BMW 328i 9.231 ## 131 Saab 5-Sep 9.191 ## 132 Lexus LX470 9.126 ## 133 Porsche Boxter 8.982 ## 134 Acura RL 8.588 ## 135 Saturn LW 8.472 ## 136 Mercedes-B SLK 7.998 ## 137 Chrysler Sebring Coupe 7.854 ## 138 Cadillac Eldorado 6.536 ## 139 Lexus LS400 6.375 ## 140 Mitsubishi Diamante 5.711 ## 141 Volkswagen GTI 5.596 ## 142 Plymouth Breeze 5.240 ## 143 Saturn SW 5.223 ## 144 Dodge Avenger 4.734 ## 145 Volvo V40 3.545 ## 146 Volvo C70 3.493 ## 147 Lexus GS400 3.334 ## 148 Mercedes-B SL-Class 3.311 ## 149 Plymouth Prowler 1.872 ## 150 Porsche Carrera Cabrio 1.866 ## 151 Mercedes-B SLK230 1.526 ## 152 Audi A8 1.380 ## 153 Porsche Carrera Coupe 1.280 ## 154 Oldsmobile Cutlass 1.112 ## 155 Mercedes-B CL500 0.954 ## 156 Dodge Viper 0.916 ## 157 Mitsubishi 3000GT 0.110
Assumption: horsepower
fig4 <- plot_ly(df,
x = ~Horsepower,
y = ~Sales_in_thousands,
type='scatter',
mode = 'markers',
hoverinfo = 'text',
text = paste('Horsepower: ', df$Horsepower,
"<br>",
'Sales in thousands: ', df$Sales_in_thousands,
"<br>",
"Manufacture: ", df$Manufacturer,
"<br>",
"Model:", df$Model),
color = ~Manufacturer,
marker= list(size =10))
fig4 <- fig4 %>% layout(
yaxis = list(zeroline = FALSE),
xaxis = list(zeroline = FALSE))
Result: Not everyone like the horsepower
Another thing come to mind is usually car’s horsepower and fuel economy.
fig3 <- plot_ly(df,
x = ~Fuel_efficiency,
y = ~ Horsepower,
type = 'scatter',
text = paste('Horsepower: ', df$Horsepower,
"<br>",
'Fuel Efficiency', df$Fuel_efficiency,
"<br>",
'Sales in thousands: ', df$Sales_in_thousands,
"<br>",
"Manufacture: ", df$Manufacturer,
"<br>",
"Model:", df$Model),
mode = 'markers',
color = ~Sales_in_thousands )
fig3 <- fig3 %>% layout(title = 'Horsepower vs Fuel Efficiency',
xaxis = list(showgrid = FALSE),
yaxis = list(showgrid = FALSE))
Fuel efficiency seems to be the favour.
Customer prefers inexpensive, fuel friendly car instead of beefy expensive car. Quite obvious to see the pllots are more concentrated on fuel friendly cars.
fig5 <- plot_ly(df, x = ~Horsepower, y = ~Price_in_thousands, z = ~Fuel_efficiency,
type ='scatter3d',
mode = 'markers',
hoverinfo = 'text',
color =~Sales_in_thousands,
text = paste("Cars sold in thousdands: ", df$Sales_in_thousands,
"<br>",
"Manufacture: ", df$Manufacturer,
"<br>",
"Model:", df$Model))
fig5 <- fig5 %>% add_markers()
Omitting the Ford F-Seires to see the better understanding of where other car model stand.
df=df[-57,]
Here, rather than looking at the total car sold, I have made a column of revenue for better understanding.Horsepower and fuel efficiency relationship is inverse proportion regardless.
df$revenue <-with(df, Sales_in_thousands * Price_in_thousands)
By plotting the given data, I was able to solve what customers are looking for when shopping for cars.At first, horsepower could be one of a good factor. However, that’s not the case, customers are looking for inexpensive and fuel friendly car like what I would pick.Ford F-Series being top could be the data is counting all of the F-Series line up(F-150, F-250 etc)